app.py

import gradio as gr
from datasets import load_dataset
from transformers import AutoTokenizer, AutoModelForQuestionAnswering, TrainingArguments, Trainer, pipeline

# Load your dataset function
dataset = load_dataset("karthikmns/eval_testing_mns")

# Load a pre-trained model and tokenizer
model_name = "distilbert-base-uncased-distilled-squad"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForQuestionAnswering.from_pretrained(model_name)

# Tokenize the dataset
def tokenize_function(examples):
    return tokenizer(examples["text"], truncation=True, padding="max_length")

tokenized_datasets = dataset.map(tokenize_function, batched=True)

# Set up training arguments
training_args = TrainingArguments(
    output_dir="./results",
    evaluation_strategy="epoch",
    learning_rate=2e-5,
    per_device_train_batch_size=16,
    per_device_eval_batch_size=16,
    num_train_epochs=3,
    weight_decay=0.01,
)

# Create Trainer instance
trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=tokenized_datasets["train"],
    eval_dataset=tokenized_datasets["validation"],
)

# Fine-tune the model
trainer.train()

# Save the model
model.save_pretrained("./fine_tuned_model")

# Create a question-answering pipeline
qa_pipeline = pipeline("question-answering", model="./fine_tuned_model")

# Define the Gradio interface function
def answer_question(question):
    result = qa_pipeline(question=question, context=dataset["text"])
    return result['answer']

# Create and launch the Gradio interface
iface = gr.Interface(
    fn=answer_question,
    inputs="text",
    outputs="text",
    title="Textbook Q&A",
    description="Ask a question about your textbook!"
)

iface.launch()